Transferability of data-driven models to predict urban pluvial flood water depth in Berlin, Germany
- Data-driven models have been recently suggested to surrogate computationally expensive hydrodynamic models to map flood hazards. However, most studies focused on developing models for the same area or the same precipitation event. It is thus not obvious how transferable the models are in space. This study evaluates the performance of a convolutional neural network (CNN) based on the U-Net architecture and the random forest (RF) algorithm to predict flood water depth, the models' transferability in space and performance improvement using transfer learning techniques. We used three study areas in Berlin to train, validate and test the models. The results showed that (1) the RF models outperformed the CNN models for predictions within the training domain, presumable at the cost of overfitting; (2) the CNN models had significantly higher potential than the RF models to generalize beyond the training domain; and (3) the CNN models could better benefit from transfer learning technique to boost their performance outside training domains thanData-driven models have been recently suggested to surrogate computationally expensive hydrodynamic models to map flood hazards. However, most studies focused on developing models for the same area or the same precipitation event. It is thus not obvious how transferable the models are in space. This study evaluates the performance of a convolutional neural network (CNN) based on the U-Net architecture and the random forest (RF) algorithm to predict flood water depth, the models' transferability in space and performance improvement using transfer learning techniques. We used three study areas in Berlin to train, validate and test the models. The results showed that (1) the RF models outperformed the CNN models for predictions within the training domain, presumable at the cost of overfitting; (2) the CNN models had significantly higher potential than the RF models to generalize beyond the training domain; and (3) the CNN models could better benefit from transfer learning technique to boost their performance outside training domains than RF models.…
Author details: | Omar SeleemORCiDGND, Georgy AyzelORCiDGND, Axel BronstertORCiDGND, Maik HeistermannORCiDGND |
---|---|
DOI: | https://doi.org/10.5194/nhess-23-809-2023 |
ISSN: | 1684-9981 |
ISSN: | 1561-8633 |
Title of parent work (English): | Natural Hazards and Earth System Sciences |
Publisher: | Copernicus |
Place of publishing: | Göttingen |
Publication type: | Article |
Language: | English |
Date of first publication: | 2023/02/24 |
Publication year: | 2023 |
Release date: | 2023/04/20 |
Volume: | 23 |
Issue: | 2 |
Number of pages: | 23 |
First page: | 809 |
Last Page: | 822 |
Funding institution: | Universität Potsdam |
Funding institution: | Deutsche Forschungsgemeinschaft (DFG) |
Funding number: | PA 2023_013 |
Funding number: | Projektnummer 491466077 |
Organizational units: | Mathematisch-Naturwissenschaftliche Fakultät / Institut für Umweltwissenschaften und Geographie |
DDC classification: | 5 Naturwissenschaften und Mathematik / 55 Geowissenschaften, Geologie / 550 Geowissenschaften |
Peer review: | Referiert |
Grantor: | Publikationsfonds der Universität Potsdam |
Publishing method: | Open Access / Gold Open-Access |
License (German): | CC-BY - Namensnennung 4.0 International |
External remark: | Zweitveröffentlichung in der Schriftenreihe Zweitveröffentlichungen der Universität Potsdam : Mathematisch-Naturwissenschaftliche Reihe ; 1323 |